Fixes for 5.15

Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/queue-5.15/kvm-downgrade-two-bug_ons-to-warn_on_once.patch b/queue-5.15/kvm-downgrade-two-bug_ons-to-warn_on_once.patch
new file mode 100644 (file)
index 0000000..4cdc87f
--- /dev/null
+++ b/queue-5.15/kvm-downgrade-two-bug_ons-to-warn_on_once.patch
@@ -0,0 +1,46 @@
+From 8130808741d5a7f05a29de484da8e93b280bc60b Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 22 Nov 2021 18:24:01 -0500
+Subject: KVM: downgrade two BUG_ONs to WARN_ON_ONCE
+
+From: Paolo Bonzini <pbonzini@redhat.com>
+
+[ Upstream commit 5f25e71e311478f9bb0a8ef49e7d8b95316491d7 ]
+
+This is not an unrecoverable situation.  Users of kvm_read_guest_offset_cached
+and kvm_write_guest_offset_cached must expect the read/write to fail, and
+therefore it is possible to just return early with an error value.
+
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ virt/kvm/kvm_main.c | 6 ++++--
+ 1 file changed, 4 insertions(+), 2 deletions(-)
+
+diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
+index ce1847bc898b2..c6bfd4e15d28a 100644
+--- a/virt/kvm/kvm_main.c
++++ b/virt/kvm/kvm_main.c
+@@ -3001,7 +3001,8 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+       int r;
+       gpa_t gpa = ghc->gpa + offset;
+ 
+-      BUG_ON(len + offset > ghc->len);
++      if (WARN_ON_ONCE(len + offset > ghc->len))
++              return -EINVAL;
+ 
+       if (slots->generation != ghc->generation) {
+               if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))
+@@ -3038,7 +3039,8 @@ int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+       int r;
+       gpa_t gpa = ghc->gpa + offset;
+ 
+-      BUG_ON(len + offset > ghc->len);
++      if (WARN_ON_ONCE(len + offset > ghc->len))
++              return -EINVAL;
+ 
+       if (slots->generation != ghc->generation) {
+               if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))
+-- 
+2.33.0
+

diff --git a/queue-5.15/kvm-selftests-make-sure-kvm_create_max_vcpus-test-wo.patch b/queue-5.15/kvm-selftests-make-sure-kvm_create_max_vcpus-test-wo.patch
new file mode 100644 (file)
index 0000000..29bbead
--- /dev/null
+++ b/queue-5.15/kvm-selftests-make-sure-kvm_create_max_vcpus-test-wo.patch
@@ -0,0 +1,90 @@
+From 54a4589964241e2679f20a61c6434711c1752cc0 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 23 Nov 2021 14:59:53 +0100
+Subject: KVM: selftests: Make sure kvm_create_max_vcpus test won't hit
+ RLIMIT_NOFILE
+
+From: Vitaly Kuznetsov <vkuznets@redhat.com>
+
+[ Upstream commit 908fa88e420f30dde6d80f092795a18ec72ca6d3 ]
+
+With the elevated 'KVM_CAP_MAX_VCPUS' value kvm_create_max_vcpus test
+may hit RLIMIT_NOFILE limits:
+
+ # ./kvm_create_max_vcpus
+ KVM_CAP_MAX_VCPU_ID: 4096
+ KVM_CAP_MAX_VCPUS: 1024
+ Testing creating 1024 vCPUs, with IDs 0...1023.
+ /dev/kvm not available (errno: 24), skipping test
+
+Adjust RLIMIT_NOFILE limits to make sure KVM_CAP_MAX_VCPUS fds can be
+opened. Note, raising hard limit ('rlim_max') requires CAP_SYS_RESOURCE
+capability which is generally not needed to run kvm selftests (but without
+raising the limit the test is doomed to fail anyway).
+
+Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
+Message-Id: <20211123135953.667434-1-vkuznets@redhat.com>
+[Skip the test if the hard limit can be raised. - Paolo]
+Reviewed-by: Sean Christopherson <seanjc@google.com>
+Tested-by: Sean Christopherson <seanjc@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ .../selftests/kvm/kvm_create_max_vcpus.c      | 30 +++++++++++++++++++
+ 1 file changed, 30 insertions(+)
+
+diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
+index 0299cd81b8ba2..aa3795cd7bd3d 100644
+--- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
++++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
+@@ -12,6 +12,7 @@
+ #include <stdio.h>
+ #include <stdlib.h>
+ #include <string.h>
++#include <sys/resource.h>
+ 
+ #include "test_util.h"
+ 
+@@ -40,10 +41,39 @@ int main(int argc, char *argv[])
+ {
+       int kvm_max_vcpu_id = kvm_check_cap(KVM_CAP_MAX_VCPU_ID);
+       int kvm_max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
++      /*
++       * Number of file descriptors reqired, KVM_CAP_MAX_VCPUS for vCPU fds +
++       * an arbitrary number for everything else.
++       */
++      int nr_fds_wanted = kvm_max_vcpus + 100;
++      struct rlimit rl;
+ 
+       pr_info("KVM_CAP_MAX_VCPU_ID: %d\n", kvm_max_vcpu_id);
+       pr_info("KVM_CAP_MAX_VCPUS: %d\n", kvm_max_vcpus);
+ 
++      /*
++       * Check that we're allowed to open nr_fds_wanted file descriptors and
++       * try raising the limits if needed.
++       */
++      TEST_ASSERT(!getrlimit(RLIMIT_NOFILE, &rl), "getrlimit() failed!");
++
++      if (rl.rlim_cur < nr_fds_wanted) {
++              rl.rlim_cur = nr_fds_wanted;
++              if (rl.rlim_max < nr_fds_wanted) {
++                      int old_rlim_max = rl.rlim_max;
++                      rl.rlim_max = nr_fds_wanted;
++
++                      int r = setrlimit(RLIMIT_NOFILE, &rl);
++                      if (r < 0) {
++                              printf("RLIMIT_NOFILE hard limit is too low (%d, wanted %d)\n",
++                                     old_rlim_max, nr_fds_wanted);
++                              exit(KSFT_SKIP);
++                      }
++              } else {
++                      TEST_ASSERT(!setrlimit(RLIMIT_NOFILE, &rl), "setrlimit() failed!");
++              }
++      }
++
+       /*
+        * Upstream KVM prior to 4.8 does not support KVM_CAP_MAX_VCPU_ID.
+        * Userspace is supposed to use KVM_CAP_MAX_VCPUS as the maximum ID
+-- 
+2.33.0
+

diff --git a/queue-5.15/kvm-vmx-clear-vmx_x86_ops.sync_pir_to_irr-if-apicv-i.patch b/queue-5.15/kvm-vmx-clear-vmx_x86_ops.sync_pir_to_irr-if-apicv-i.patch
new file mode 100644 (file)
index 0000000..579a879
--- /dev/null
+++ b/queue-5.15/kvm-vmx-clear-vmx_x86_ops.sync_pir_to_irr-if-apicv-i.patch
@@ -0,0 +1,38 @@
+From aff57bd1c1bda4b2f0b4c5d92854f837fec88a0e Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 30 Nov 2021 07:36:41 -0500
+Subject: KVM: VMX: clear vmx_x86_ops.sync_pir_to_irr if APICv is disabled
+
+From: Paolo Bonzini <pbonzini@redhat.com>
+
+[ Upstream commit e90e51d5f01d2baae5dcce280866bbb96816e978 ]
+
+There is nothing to synchronize if APICv is disabled, since neither
+other vCPUs nor assigned devices can set PIR.ON.
+
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/vmx/vmx.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
+index dacdf2395f01a..4e212f04268bb 100644
+--- a/arch/x86/kvm/vmx/vmx.c
++++ b/arch/x86/kvm/vmx/vmx.c
+@@ -7776,10 +7776,10 @@ static __init int hardware_setup(void)
+               ple_window_shrink = 0;
+       }
+ 
+-      if (!cpu_has_vmx_apicv()) {
++      if (!cpu_has_vmx_apicv())
+               enable_apicv = 0;
++      if (!enable_apicv)
+               vmx_x86_ops.sync_pir_to_irr = NULL;
+-      }
+ 
+       if (cpu_has_vmx_tsc_scaling()) {
+               kvm_has_tsc_control = true;
+-- 
+2.33.0
+

diff --git a/queue-5.15/kvm-x86-fix-tlb-flush-for-tdp-in-kvm_invalidate_pcid.patch b/queue-5.15/kvm-x86-fix-tlb-flush-for-tdp-in-kvm_invalidate_pcid.patch
new file mode 100644 (file)
index 0000000..6f79c1a
--- /dev/null
+++ b/queue-5.15/kvm-x86-fix-tlb-flush-for-tdp-in-kvm_invalidate_pcid.patch
@@ -0,0 +1,51 @@
+From 8cb8f818be6f46e87ff6397ea429852357f8048c Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 19 Oct 2021 19:01:51 +0800
+Subject: KVM: X86: Fix tlb flush for tdp in kvm_invalidate_pcid()
+
+From: Lai Jiangshan <laijs@linux.alibaba.com>
+
+[ Upstream commit e45e9e3998f0001079b09555db5bb3b4257f6746 ]
+
+The KVM doesn't know whether any TLB for a specific pcid is cached in
+the CPU when tdp is enabled.  So it is better to flush all the guest
+TLB when invalidating any single PCID context.
+
+The case is very rare or even impossible since KVM generally doesn't
+intercept CR3 write or INVPCID instructions when tdp is enabled, so the
+fix is mostly for the sake of overall robustness.
+
+Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
+Message-Id: <20211019110154.4091-2-jiangshanlai@gmail.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/x86.c | 12 ++++++++++++
+ 1 file changed, 12 insertions(+)
+
+diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
+index eff065ce6f8e8..3c9e2d236830c 100644
+--- a/arch/x86/kvm/x86.c
++++ b/arch/x86/kvm/x86.c
+@@ -1091,6 +1091,18 @@ static void kvm_invalidate_pcid(struct kvm_vcpu *vcpu, unsigned long pcid)
+       unsigned long roots_to_free = 0;
+       int i;
+ 
++      /*
++       * MOV CR3 and INVPCID are usually not intercepted when using TDP, but
++       * this is reachable when running EPT=1 and unrestricted_guest=0,  and
++       * also via the emulator.  KVM's TDP page tables are not in the scope of
++       * the invalidation, but the guest's TLB entries need to be flushed as
++       * the CPU may have cached entries in its TLB for the target PCID.
++       */
++      if (unlikely(tdp_enabled)) {
++              kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
++              return;
++      }
++
+       /*
+        * If neither the current CR3 nor any of the prev_roots use the given
+        * PCID, then nothing needs to be done here because a resync will
+-- 
+2.33.0
+

diff --git a/queue-5.15/series b/queue-5.15/series
index aee4735be173b14fba01fa31a0d525f308c60d1f..263f27fa49e58f416689abc4aadf78ac327cab11 100644 (file)
--- a/queue-5.15/series
+++ b/queue-5.15/series
@@ -40,3 +40,8 @@ tracing-fix-a-kmemleak-false-positive-in-tracing_map.patch
 staging-most-dim2-use-device-release-method.patch
 fuse-make-sure-reclaim-doesn-t-write-the-inode.patch
 perf-inject-fix-itrace-space-allowed-for-new-attributes.patch
+kvm-vmx-clear-vmx_x86_ops.sync_pir_to_irr-if-apicv-i.patch
+kvm-selftests-make-sure-kvm_create_max_vcpus-test-wo.patch
+kvm-downgrade-two-bug_ons-to-warn_on_once.patch
+x86-kvm-remove-unused-ack_notifier-callbacks.patch
+kvm-x86-fix-tlb-flush-for-tdp-in-kvm_invalidate_pcid.patch

diff --git a/queue-5.15/x86-kvm-remove-unused-ack_notifier-callbacks.patch b/queue-5.15/x86-kvm-remove-unused-ack_notifier-callbacks.patch
new file mode 100644 (file)
index 0000000..328c9b9
--- /dev/null
+++ b/queue-5.15/x86-kvm-remove-unused-ack_notifier-callbacks.patch
@@ -0,0 +1,49 @@
+From 172edff19a8068fabe1d77c908708244cc45e981 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 17 Nov 2021 08:16:17 +0100
+Subject: x86/kvm: remove unused ack_notifier callbacks
+
+From: Juergen Gross <jgross@suse.com>
+
+[ Upstream commit 9dba4d24cbb5524dd39ab1e08886373b17f07ff2 ]
+
+Commit f52447261bc8c2 ("KVM: irq ack notification") introduced an
+ack_notifier() callback in struct kvm_pic and in struct kvm_ioapic
+without using them anywhere. Remove those callbacks again.
+
+Signed-off-by: Juergen Gross <jgross@suse.com>
+Message-Id: <20211117071617.19504-1-jgross@suse.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/ioapic.h | 1 -
+ arch/x86/kvm/irq.h    | 1 -
+ 2 files changed, 2 deletions(-)
+
+diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
+index 27e61ff3ac3e8..f1b2b2a6ff4db 100644
+--- a/arch/x86/kvm/ioapic.h
++++ b/arch/x86/kvm/ioapic.h
+@@ -81,7 +81,6 @@ struct kvm_ioapic {
+       unsigned long irq_states[IOAPIC_NUM_PINS];
+       struct kvm_io_device dev;
+       struct kvm *kvm;
+-      void (*ack_notifier)(void *opaque, int irq);
+       spinlock_t lock;
+       struct rtc_status rtc_status;
+       struct delayed_work eoi_inject;
+diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
+index 650642b18d151..c2d7cfe82d004 100644
+--- a/arch/x86/kvm/irq.h
++++ b/arch/x86/kvm/irq.h
+@@ -56,7 +56,6 @@ struct kvm_pic {
+       struct kvm_io_device dev_master;
+       struct kvm_io_device dev_slave;
+       struct kvm_io_device dev_elcr;
+-      void (*ack_notifier)(void *opaque, int irq);
+       unsigned long irq_states[PIC_NUM_PINS];
+ };
+ 
+-- 
+2.33.0
+